Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

SqueezeOS — Institutional AI Market Intelligence

REMOTE · SQUEEZEOS-API.ONRENDER.COM · SCANNED SEP 25

Institutional AI market intelligence: squeeze scanner, options flow, council verdicts. x402 RLUSD.

0 this week 71 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security80
Transport & Reachability100
Schema Quality & AI Usability72
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 942 tokens (~62/item across 15 items; 15 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management4
  • Stability check failed: schema churn in the 30 days we've observed: 69 tool removals, 0 breaking changes, 0 auth/transport breaks, 12 additions. See how to fix → Fail
Tool Coverage74
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 21% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the SqueezeOS — Institutional AI Market Intelligence MCP server?

SqueezeOS — Institutional AI Market Intelligence is a hosted endpoint at https://squeezeos-api.onrender.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · squeezeos-api.onrender.com

# add to Claude Code
claude mcp add --transport http timwal78-squeezeos 'https://squeezeos-api.onrender.com/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "timwal78-squeezeos": {
      "url": "https://squeezeos-api.onrender.com/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "timwal78-squeezeos": {
      "type": "http",
      "url": "https://squeezeos-api.onrender.com/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.timwal78-squeezeos]
url = "https://squeezeos-api.onrender.com/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "timwal78-squeezeos": {
      "type": "remote",
      "url": "https://squeezeos-api.onrender.com/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add timwal78-squeezeos --url 'https://squeezeos-api.onrender.com/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  timwal78-squeezeos:
    url: "https://squeezeos-api.onrender.com/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "timwal78-squeezeos": {
      "Transport": "http",
      "Url": "https://squeezeos-api.onrender.com/mcp"
    }
  }
}
# add to Vellum
assistant mcp add timwal78-squeezeos -t streamable-http -u 'https://squeezeos-api.onrender.com/mcp'
// mcp.json
{
  "mcpServers": {
    "timwal78-squeezeos": {
      "type": "http",
      "url": "https://squeezeos-api.onrender.com/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 19 Sept 26 0
    • Tool coverage: 26% → 21% ▼ functional
    • Schema quality: 69 → 62 ▲ functional
    • New tool “aftersearch_accept” functional
    • New tool “aftersearch_quote” functional
    • New tool “aftersearch_resolve” functional
    • New tool “aftersearch_verify_serp” functional
  • 2 Sept 26 0
    • Schema quality: 642 → 766 ▼ functional
    • Tool coverage: 19% → 26% ▲ functional
    • New tool “agent_web_access” functional
  • 1 Sept 26 0
    • Tool “call_capability” rewrote its description, which is the text the model reads security
    • Tool coverage: 13% → 19% ▲ functional
    • “call_capability” added an optional parameter “alternative_intent” cosmetic
  • 31 Aug 26 −3
    • Tool “agent_economy” was removed ▼ security
    • Tool “agent_routes_discover” was removed ▼ security
    • Tool “agentbids_discover” was removed ▼ security
    • Tool “audit_information_gain” was removed ▼ security
    • Tool “autopilot_start” was removed ▼ security
    • Tool “autopilot_status” was removed ▼ security
    • Tool “autopilot_stop” was removed ▼ security
    • Tool “autopilot_trades” was removed ▼ security
    • Tool “bazaar_negotiator_discover” was removed ▼ security
    • Tool “beastmode_scan” was removed ▼ security
    • Tool “build_entity_schema” was removed ▼ security
    • Tool “capabilities_feed” was removed ▼ security
    • Tool “ccs_info” was removed ▼ security
    • Tool “ccs_leaderboard” was removed ▼ security
    • Tool “ccs_report” was removed ▼ security
    • Tool “ccs_score” was removed ▼ security
    • Tool “ccs_stats” was removed ▼ security
    • Tool “ccs_validate” was removed ▼ security
    • Tool “circuit_breaker_reset” was removed ▼ security
    • Tool “citation_score” was removed ▼ security
    • Tool “convergence_check” was removed ▼ security
    • Tool “council_verdict” was removed ▼ security
    • Tool “demo_council” was removed ▼ security
    • Tool “extract_aeo_blocks” was removed ▼ security
    • Tool “fred_preview” was removed ▼ security
    • Tool “fred_series” was removed ▼ security
    • Tool “futures_browse” was removed ▼ security
    • Tool “futures_create” was removed ▼ security
    • Tool “futures_leaderboard” was removed ▼ security
    • Tool “futures_take” was removed ▼ security
    • Tool “generate_additive_hook” was removed ▼ security
    • Tool “hiring_browse_jobs” was removed ▼ security
    • Tool “hiring_post_job” was removed ▼ security
    • Tool “iam_resolve” was removed ▼ security
    • Tool “iam_truth” was removed ▼ security
    • Tool “inspect_freshness” was removed ▼ security
    • Tool “ipo_price_range_history” was removed ▼ security
    • Tool “ipo_timeline” was removed ▼ security
    • Tool “ipo_upcoming” was removed ▼ security
    • Tool “iwm_odte” was removed ▼ security
    • Tool “knowledge_fabric_query” was removed ▼ security
    • Tool “macro_741_scan” was removed ▼ security
    • Tool “market_scan” was removed ▼ security
    • Tool “marketplace_browse” was removed ▼ security
    • Tool “marketplace_list_signal” was removed ▼ security
    • Tool “marketplace_read_signal” was removed ▼ security
    • Tool “memory_recall” was removed ▼ security
    • Tool “memory_stats” was removed ▼ security
    • Tool “memory_store” was removed ▼ security
    • Tool “mesh_discover” was removed ▼ security
    • Tool “narrative_optimize” was removed ▼ security
    • Tool “options_intelligence” was removed ▼ security
    • Tool “oracle_feeds” was removed ▼ security
    • Tool “oracle_query” was removed ▼ security
    • Tool “post_to_slack” was removed ▼ security
    • Tool “proprietary_ema_signal” was removed ▼ security
    • Tool “provider_score” was removed ▼ security
    • Tool “quick_headline” was removed ▼ security
    • Tool “quick_quote” was removed ▼ security
    • Tool “quick_search” was removed ▼ security
    • Tool “recommend_tool” was removed ▼ security
    • Tool “robinhood_rwa_intelligence” was removed ▼ security
    • Tool “semantic_gaps” was removed ▼ security
    • Tool “settlement_browse” was removed ▼ security
    • Tool “settlement_create” was removed ▼ security
    • Tool “settlement_trigger” was removed ▼ security
    • Tool “signal_history” was removed ▼ security
    • Tool “signal_preview” was removed ▼ security
    • Tool “sovereign_365” was removed ▼ security
    • Tool “sovereign_741” was removed ▼ security
    • Tool “sovereign_full” was removed ▼ security
    • Tool “sovereign_triplelock” was removed ▼ security
    • Tool “truth_verify” was removed ▼ security
    • Tool “try_capability” was removed ▼ security
    • Authorization: unverified → partial ▲ security
    • The server rewrote its instructions, which are the text every model session reads security
    • The server changed its declared name: squeezeos → SCRIPTMASTERLABS — SqueezeOS security
    • Tool “compare_capabilities” rewrote its description, which is the text the model reads security
    • Tool “inspect_capability” rewrote its description, which is the text the model reads security
    • Tool “system_status” rewrote its description, which is the text the model reads security
    • Tool coverage: 72% → 13% ▼ functional
    • MCP protocol: fail → pass ▲ functional
    • Schema quality: fail → pass ▲ functional
    • The server now declares the “prompts” capability functional
    • The server now declares the “resources” capability functional
    • Schema quality: excellent → good functional
    • MCP protocol version: 2024-11-05 → 2026-07-28 functional
    • Server version: 5.0.0 → 8.3.0 functional
    • New tool “call_capability” functional
    • New tool “capability_manifest” functional
    • New tool “discover_capabilities” functional
    • New tool “recommend_capability” functional
    • New tool “x402_contract” functional
    • New tool “x402_evidence” functional
    • New tool “x402_readiness” functional
    • “compare_capabilities” reworded the description of “probe” cosmetic
    • “compare_capabilities” reworded the description of “sml_ids” cosmetic
    • “inspect_capability” reworded the description of “probe” cosmetic
    • “inspect_capability” reworded the description of “sml_id” cosmetic
    • Tool “compare_capabilities” changed its title: Compare Capabilities cosmetic
    • Tool “inspect_capability” changed its title: Inspect Capability cosmetic
    • Tool “system_status” changed its title: System Status cosmetic
  • 28 Aug 26 +51
    • Stability: unverified → fail ▼ security
    • Injection markers: unverified → pass ▲ security
    • HSTS header: fail → pass ▲ security
    • Transport: fail → pass ▲ security
    • Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 77 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. security
    • MCP protocol: unverified → fail ▼ functional
    • Endpoint reachability: not serving MCP → reachable ▲ functional
    • Tool coverage: unverified → 100 ▲ functional
    • New tool “agent_routes_discover” functional
    • New tool “agentbids_discover” functional
    • New tool “bazaar_negotiator_discover” functional
    • New tool “knowledge_fabric_query” functional
    • New tool “robinhood_rwa_intelligence” functional
  • 27 Aug 26 23
    • Endpoint reachability: reachable → not serving MCP ▼ security
    • Stability: fail → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Transport: pass → fail ▼ security
    • HSTS header: pass → fail ▼ security
    • Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the whole tool list to see what that exposes. security
    • Capabilities: fail → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
  • 26 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 25 Sept 2026 · Probed https://squeezeos-api.onrender.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=onrender.com CN=WE1,O=Google Trust Services,C=US 21 Sept 2026 20 Dec 2026 ECDSA 256 ECDSA-SHA256 6eb1e3fe7d0631ea1337bfa4a321c137
SANs: onrender.com, *.onrender.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of squeezeos-api.onrender.com. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
onrender.com. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains
content-security-policy default-src 'self'; style-src 'self' 'unsafe-inline'; img-src 'self' data:
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://squeezeos-api.onrender.com/mcp Verified 200
http (plaintext) http://squeezeos-api.onrender.com/mcp HTTPS enforced 301 https://squeezeos-api.onrender.com/mcp
MCP tools · 15 exposed · ~883 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
aftersearch_accept ~55

Retry one immutable job with caller-supplied x402 authorization. payment_response is forwarded as PAYMENT-SIGNATURE; SML never signs or spends.

NameTypeReqDescription
job_idstringyes–
payment_responsestringyes–

No output schema declared.

No examples provided.

aftersearch_quote ~38

Return fresh x402 PAYMENT-REQUIRED terms for one immutable job. A 402 is not payment.

NameTypeReqDescription
job_idstringyes–

No output schema declared.

No examples provided.

aftersearch_resolve ~38

Compile a query into intent, bounded Evidence Pack, immutable job and fresh-quote pointer; never spends.

NameTypeReqDescription
querystringyes–

No output schema declared.

No examples provided.

aftersearch_verify_serp ~45

Verify pasted SERP/AI text or one caller-provided public URL; returns confirm, contradict or missing with sources.

NameTypeReqDescription
serp_text_or_urlstringyes–

No output schema declared.

No examples provided.

agent_web_access ~124

Use SML Agent Web Access: give an AI agent one public HTTPS URL and receive compact LLM-ready Markdown through the stable Clean Web Reader service. No separate SML account or API key is required. An unsigned call returns the live x402 PAYMENT-REQUIRED challenge and never auto-spends; retry only with a challenge-specific payment_signature.

NameTypeReqDescription
max_charsinteger––
payment_signaturestring–Canonical x402 v2 PAYMENT-SIGNATURE bound to this exact Agent Web Access challenge.
urlstringyesPublic HTTPS URL to read.

No output schema declared.

No examples provided.

call_capability ~205

Call a concrete SqueezeOS REST path on the canonical public host. GET is read-only. POST requires confirm_write=true. If the target returns 402 and no payment_signature was supplied, this tool preserves PAYMENT-REQUIRED and returns the closest no-spend SML alternative from the Capability Router. Retry the original route only with a challenge-specific payment_signature. Sensitive operator/control routes and arbitrary auth headers are not exposed.

NameTypeReqDescription
alternative_intentstring–Optional natural-language intent used to rank the closest SML alternative after an unsigned HTTP 402.
bodyobject|array|string|number|boolean|null––
confirm_writeboolean––
methodstringyes–
pathstringyesConcrete SqueezeOS path beginning with /; do not pass a full URL.
payment_signaturestring–Canonical x402 v2 PAYMENT-SIGNATURE value bound to this exact target-resource challenge.
queryobject––

No output schema declared.

No examples provided.

capability_manifest ~34

Return the current machine capability manifest generated from the running Flask route table. This is the canonical product-inventory authority for MCP discovery.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

compare_capabilities ~49

Compare 2-5 live capabilities using the same real metadata returned by inspect_capability; no fabricated composite score is produced.

NameTypeReqDescription
probeboolean––
sml_idsarrayyes–

No output schema declared.

No examples provided.

discover_capabilities ~62

Search the live SqueezeOS capability inventory. Lexical mode is always available; unified mode may add configured evidence-backed semantic/graph context without fabricating scores.

NameTypeReqDescription
limitinteger––
modestring––
querystringyes–

No output schema declared.

No examples provided.

inspect_capability ~55

Inspect one live capability by sml_id. Returns its real endpoint/payment metadata and, when safe, a real liveness probe rather than an invented reliability score.

NameTypeReqDescription
probeboolean––
sml_idstringyes–

No output schema declared.

No examples provided.

recommend_capability ~47

Return the best matching real SqueezeOS capabilities for a natural-language need, including live endpoint/payment metadata and next actions.

NameTypeReqDescription
limitinteger––
querystringyes–

No output schema declared.

No examples provided.

system_status ~30

Read the live SqueezeOS status endpoint. The MCP server does not synthesize cluster-health or synchronization claims.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

x402_contract ~40

Return the canonical SqueezeOS x402 v2 discovery contract. Exact spend terms remain authoritative only in the target resource's fresh PAYMENT-REQUIRED challenge.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

x402_evidence ~36

Read real settlement evidence recorded by the canonical x402 rail. A challenge or signature alone is never treated as revenue or settlement proof.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

x402_readiness ~25

Read the live canonical payment-rail readiness surface before attempting a paid call.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Common questions

What is the SqueezeOS — Institutional AI Market Intelligence MCP server?

SqueezeOS — Institutional AI Market Intelligence is an MCP server listed in the public MCP registry as io.github.Timwal78/squeezeos. Institutional AI market intelligence: squeeze scanner, options flow, council verdicts. x402 RLUSD. This page covers its hosted endpoint (https://squeezeos-api.onrender.com/mcp).

Is the SqueezeOS — Institutional AI Market Intelligence MCP server safe to use?

SqueezeOS — Institutional AI Market Intelligence scores 71 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the SqueezeOS — Institutional AI Market Intelligence MCP server expose?

SqueezeOS — Institutional AI Market Intelligence exposes 15 tools: discover_capabilities, recommend_capability, inspect_capability, compare_capabilities, capability_manifest, and 10 more. Their descriptions and schemas cost roughly 883 tokens of context every time the server is loaded.

Does the SqueezeOS — Institutional AI Market Intelligence MCP server require authentication?

No. We connected to SqueezeOS — Institutional AI Market Intelligence without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the SqueezeOS — Institutional AI Market Intelligence MCP server still maintained?

SqueezeOS — Institutional AI Market Intelligence is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.